Mixed Methods Research research where the researcher uses qualitative and quantitative research in a single study psychological research has been primarily quantitative much more prevalent in the science world recently there is a big push towards doing more quantitative methods quantitative research strengths lot more people and quicker and easier to do ndings can be generalized to the larger population confounding variables can be controlled collecting and analyzing data can often take place in a relatively short time useful for studying large numbers of people weaknesses correlations may be found that arent generalizable researchers may mis out on things by focusing too much on the big picture knowledge produced may be too general to apply to speci c local situations contexts and cultures qualitative research strengths weaknesses mixed methods strengths data based off participants own construction of experiences provides rich detail useful for describing complex phenomena knowledge produced may not generalize well to other settings and participants more dif cult to test hypotheses and theories data analysis is often very time consuming words pictures and narrative can add strength and clarity to numeric results can address a broader range of research questions can use strengths and weaknesses of each approach to build off one another mixed methods weakness can be dif cult for a single researcher to accomplish often expensive and time consuming mixed methods designs equal status of quan and qual concurrent doing both at the same time dominant status of one or the other sequential which one is rst and how much time do you devote to each Experimental Method Review confounding variables variables that vary along with the independent variable need to be controlled or eliminated experiment must be designed so that the independent variable is the only cause of the results basic experiments internal validity posttest only design three steps obtain two equivalent groups of participants random assignment into groups introduce the independent variable experimental vs control group measure the effect of the indnependent variable on the dependent variable pretest posttest design almost identitical but a pretest is given prior to any treatment or experimental manipulation makes it possible to determine if group are equivalant from the beginning randomization of above 20 people per group makes this most likely unessesary advantages possible to check for non equivalant groups useful for selecting participants based on a certain criterion or set of criteria nessesary when there is a risk that participants will drop out experimental mortality attribution if we have pretest scores we can assess the differences between the people that dropped and the people that stayed disadvantages can be time consuming may potentially give away the hypothesis of the experiment and therefore bias participant behavior you can assess the impact of a pretest using solomen four group design do a control and experimental group with using a pretest and not using one assigning participants to conditions three basic ways independent group design each person participates in only one group random assignment is used to assign participants to conditions random assignment prevents systematic biases repeated measures design each person is assigned to both experimental groups do the experiment twice problem is that you get a practice effect because people have read the same thing twice advantages fewer research participants needed extremely sensitive to nding statistically signi cant differences between groups because is easier to seperate the systematic individual differences from the effect of the independent variable counter balancing having another group do the same test but doing the test ipped so eliminates practice effect disadvantges order effects the order of presenting the treatment affects the dependent variable practice effect an improvement in performance as a result of repeated prctice with a task fatigue effect deterioration in performance as the participant becomes tired bored or distracted carryover effect the effect of the rst treatment carries over to in uence the response to the second treatment high stress vs low stress deal with these by counterbalancing or increasing the time between the tests counterbalancing latin squares all possible orders of presentation are included in the experiment can get overwhelming very quickly a limited set of orders constructed to ensure each condition appears at each ordinal position each condition precedes and follows each condition one time time interval between treatments rest periods may counteract fatigue effects attending to an unrelated task between treatments may reduce the possibility of a carryover effect experiments that extend over too much time may make recruitment of participants dif cult and may increase experimental mortality rst match participants on a certain characteristic and assign one to the treatment group and then one to the control goal acheive the same equivalancy within groups that you obtain in a repeated measure matched pairs design conducting experiments straight forward mnipulation researchers manipulate the independent variable using written verbal or visual material naaive theories of intelligence fake scienti c article that states that intelligence is genetic and unchanging throughout someone life fake scienti c article that states that intelligence is malleable and can be improved throughtou ones life manipulating their beliefs goldtein cialdini and griskevicius ind written content of igns encouraging guests to reuse their towels dependent how many guests reused their towels one sign saying save the environment one sign says 75 of other guest reuse their towels you can too staged manipulation events that occur during the experiment are staged in order to manipulate the independent variable frequently employ a confederate these demnd creativity and acting ability on the part of the confederate asch line study conformity strength of the manipulation which line is the same length as the other line the differences between the groups should be maximized would want to totally dissagree with the subject or totally agree important to consider levels of the variable in the real world ethics cost measuring the dependent variable general categories of variables self report behavioral physiological multiple easures cost sesitivity ceiling effects