Tag: Paired Sample

Quant: Paired Sample Statistics in SPSS

Introduction

The aim of this analysis is to conduct a comparison of productivity under two organizational structures: The data are artificial estimates of productivity with column 1 representing traditional vertical management and column 2 representing other autonomous work teams (ATW). The background is that a company of 100 factory workers had been operating under traditional vertical management and decided to move to ATW. The same employees were involved in both systems having first worked under vertical management and then being converted to ATW.

From the SPSS outputs the goal is to:

  • Analyze the productivity levels of the 2 management approaches, and decide which is superior.

Hypothesis

  • Null: There is no basis of difference between the prodpre and prodpost
  • Alternative: There is are real differences between the prodpre and prodpost

Methodology

For this project, the atw.sav file is loaded into SPSS (ATW, n.d.).  The goal is to look at the relationships between the following variables: prodpre (productivity level preceding the new process) and prodpost (productivity level following the new process). To conduct a parametric analysis, navigate to Analyze > Compare Means > Paired-Samples T Test.  The variable prodpre was placed in the “Paired Variables” box under “Pair” 1 and “Variable 1”, and prodpost was placed under “Pair” 1 and “Variable 2”.  The procedures for this analysis are provided in video tutorial form by Miller (n.d.). The following output was observed in the next three tables.

Results

Table 1: Paired Sample Statistics

Mean N Std. Deviation Std. Error Mean
Pair 1 productivity level preceding the new process 76.43 100 16.820 1.682
productivity level following the new process 84.24 100 9.797 .980

Descriptively, productivity on average increased by 8 points, and the standard deviation about the mean decreased by 7 points.  This means that the estimates of productivity under the traditional vertical management are less than and showcase a wider spread than those of the estimates of productivity under the autonomous work teams.  Essentially these distributions tell the story that the workers are getting better productivity estimates with less deviation under autonomous work teams.

Table 2: Paired Samples Correlation

N Correlation Sig.
Pair 1 productivity level preceding the new process & productivity level following the new process 100 .040 .695

Based on Table 2, there is a weak correlation (r = 0.040) between the estimates of productivity under the traditional vertical management and the autonomous work teams.  Although correlation does not imply causation.

Table 3: Paired Samples Test

Paired Differences t df Sig. (2-tailed)
Mean Std. Deviation Std. Error Mean 95% Confidence Interval of the Difference
Lower Upper
Pair 1 productivity level preceding the new process – productivity level following the new process -7.817 19.126 1.913 -11.612 -4.022 -4.087 99 .000

Based on the results from the 2-tailed student t-tests (Table 3), the null hypothesis can be rejected.  There is a significant difference between the two variables prodpre and prodpost at the 0.05 level or less.  The data based on 100 workers (with degrees of freedom of 99) show that there is a significance in the estimates of productivity under the traditional vertical management and the autonomous work teams.

SPSS Code

DATASET NAME DataSet1 WINDOW=FRONT.

T-TEST PAIRS=prodpre WITH prodpost (PAIRED)

  /CRITERIA=CI(.9500)

  /MISSING=ANALYSIS.

References: